Browser Automation

Playwright MCP

Microsoft's Playwright exposed as an MCP server. Cross-browser automation for Chromium, Firefox, and WebKit.

100% Pass 🏆Free to Test 🆓Tested 📅
100% (5/5 tasks)
View on GitHubby Microsoft

Benchmark results

Pass Rate
100%(5 tasks)
100% (5/5 tasks)
Speed607ms p50607ms p50
Tested OnJun 8, 202623 tools found
MetricValue
Tools discovered23 tools found
ScopeLocal only
PricingFree
Auth requirementNone. Free to test
Verdict100% pass rate on 5 tasks

Install config

Claude Desktop (macOS)
{"mcpServers": {"playwright": {"command": "npx", "args": ["-y", "@playwright/mcp@latest"]}}}
Cursor
{"mcpServers": {"playwright": {"command": "npx", "args": ["-y", "@playwright/mcp@latest"]}}}
VS Code
// .vscode/mcp.json
{
  "servers": {
    "playwright": {
      "command": "npx",
      "args": ["-y", "@playwright/mcp@latest"]
    }
  }
}

Pros

  • +Server starts successfully
  • +Tools are discoverable

Cons

    Best for

    Cross-browser testing, scraping, and automation workflows

    Related servers in Browser Automation

    Frequently asked questions

    How do I install Playwright MCP?

    Copy the config above into your AI assistant's MCP settings file:

    • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Cursor: Settings → MCP → Add Server
    • VS Code: .vscode/mcp.json
    Does it require an API key?

    No. Playwright MCP is free to test. No API key or signup required. We tested it independently.

    How were these results measured?

    We run each server through a standardized test harness that:

    1. Installs the server via npx in a fresh environment
    2. Discovers available tools using the MCP SDK
    3. Executes real tasks (navigate, click, screenshot, etc.)
    4. Validates outputs with semantic assertions (not string matching)
    5. Measures latency percentiles and pass rate

    All test scripts are open source on GitHub.

    Related categories